license: apache-2.0
datasets:
- b-mc2/sql-create-context
- Clinton/Text-to-sql-v1
language:
- en
base_model:
- cssupport/t5-small-awesome-text-to-sql
- google-t5/t5-small
pipeline_tag: text2text-generation
tags:
- text2sql
- sql
metrics:
- accuracy
- character
library_name: transformers
Industry standard text to sql generation with high accuracy.
Sample code to begin with:
import torch from transformers import T5Tokenizer, T5ForConditionalGeneration tokenizer = T5Tokenizer.from_pretrained('anilajax/text2sql_industry_standard')
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model = T5ForConditionalGeneration.from_pretrained('anilajax/text2sql_industry_standard') model = model.to(device) model.eval()
def generate_sql(input_prompt): # Tokenize the input prompt inputs = tokenizer(input_prompt, padding=True, truncation=True, return_tensors="pt").to(device)
# Forward pass
with torch.no_grad():
outputs = model.generate(**inputs, max_length=512)
# Decode the output IDs to a string (SQL query in this case)
generated_sql = tokenizer.decode(outputs[0], skip_special_tokens=True)
return generated_sql
input_prompt = "provide count of students where class = 10"
generated_sql = generate_sql(input_prompt)
print(f"The generated SQL query is: {generated_sql}") #expected output - SELECT COUNT(*) FROM students WHERE class = 10